anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

GLM 4.7 on Zai coding plan puts tool calls inside the thinking/reasoning tag. #4114

New Issue
Open
opened 2026-02-16 17:42:40 -05:00 by yindo · 26 comments
yindo commented 2026-02-16 17:42:40 -05:00
Owner
Copy Link
Copy Source

Originally created by @greggh on GitHub (Jan 2, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

This happens to me about 15 times a day, and it forces me to start a new session because the session with that call in the thinking tag keeps happening and more errors and failures to call the right tools starts to happen.

Restarting in a new session it will go an hour or so before doing it again and needing a restart.

OpenCode version

1.0.223

Steps to reproduce

  1. Choose Zai coding plan and give it your API Key.
  2. Use GLM 4.7 for awhile.
  3. It usually happens after context goes above 100k.

Screenshot and/or share link

Image

Operating System

macOS 26.1

Terminal

Kitty

p.s. OpenCode is awesome.

Originally created by @greggh on GitHub (Jan 2, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description This happens to me about 15 times a day, and it forces me to start a new session because the session with that call in the thinking tag keeps happening and more errors and failures to call the right tools starts to happen. Restarting in a new session it will go an hour or so before doing it again and needing a restart. ### OpenCode version 1.0.223 ### Steps to reproduce 1. Choose Zai coding plan and give it your API Key. 2. Use GLM 4.7 for awhile. 3. It usually happens after context goes above 100k. ### Screenshot and/or share link <img width="1800" height="556" alt="Image" src="https://github.com/user-attachments/assets/ed24858f-82cd-4478-adeb-cad506e0b78f" /> ### Operating System macOS 26.1 ### Terminal Kitty p.s. OpenCode is awesome.
yindo added the bug label 2026-02-16 17:42:40 -05:00
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Jan 2, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #6486: Error "reasoning part reasoning-0 not found" from tool calls using GLM 4.5 Air

Both issues involve GLM models having problems with reasoning/thinking tags and tool calls, though with different error messages. Checking #6486 may provide additional context for understanding and fixing the issue.

Feel free to ignore if this doesn't address your specific case.

@github-actions[bot] commented on GitHub (Jan 2, 2026): This issue might be a duplicate of existing issues. Please check: - #6486: Error "reasoning part reasoning-0 not found" from tool calls using GLM 4.5 Air Both issues involve GLM models having problems with reasoning/thinking tags and tool calls, though with different error messages. Checking #6486 may provide additional context for understanding and fixing the issue. Feel free to ignore if this doesn't address your specific case.
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@arsham commented on GitHub (Jan 2, 2026):

This is actually handy. I was wondering when we would see such thing. Basically during the reasoning phase, the model could use a tool call to enrich its reasoning.

@arsham commented on GitHub (Jan 2, 2026): This is actually handy. I was wondering when we would see such thing. Basically during the reasoning phase, the model could use a tool call to enrich its reasoning.
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@greggh commented on GitHub (Jan 2, 2026):

This is actually handy. I was wondering when we would see such thing. Basically during the reasoning phase, the model could use a tool call to enrich its reasoning.

Definitely. I am not saying it's a horrible thing that it's calling a tool while reasoning, but isn't the best that the tool call doesn't actually happen and the session gets into a weird state for me.

@greggh commented on GitHub (Jan 2, 2026): > This is actually handy. I was wondering when we would see such thing. Basically during the reasoning phase, the model could use a tool call to enrich its reasoning. Definitely. I am not saying it's a horrible thing that it's calling a tool while reasoning, but isn't the best that the tool call doesn't actually happen and the session gets into a weird state for me.
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 2, 2026):

how consistent is this?

@rekram1-node commented on GitHub (Jan 2, 2026): how consistent is this?
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@msmirnyagin commented on GitHub (Jan 2, 2026):

@rekram1-node haha, Interleaved thinking
We support interleaved thinking by default (supported since GLM-4.5), allowing GLM to think between tool calls and after receiving tool results. This enables more complex, step-by-step reasoning: interpreting each tool output before deciding what to do next, chaining multiple tool calls with reasoning steps, and making finer-grained decisions based on intermediate results. https://docs.z.ai/guides/capabilities/thinking-mode

@msmirnyagin commented on GitHub (Jan 2, 2026): @rekram1-node haha, Interleaved thinking We support interleaved thinking by default (supported since GLM-4.5), allowing GLM to think between tool calls and after receiving tool results. This enables more complex, step-by-step reasoning: interpreting each tool output before deciding what to do next, chaining multiple tool calls with reasoning steps, and making finer-grained decisions based on intermediate results. https://docs.z.ai/guides/capabilities/thinking-mode
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 2, 2026):

@msmirnyagin we do send reasoning content back under the reasoning_content field, hmmm

Ill look

Only thing I see that may be an issue is “clear_thinking”: false but for the coding plan it says enabled by default hm

@rekram1-node commented on GitHub (Jan 2, 2026): @msmirnyagin we do send reasoning content back under the reasoning_content field, hmmm Ill look Only thing I see that may be an issue is `“clear_thinking”: false` but for the coding plan it says enabled by default hm
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 2, 2026):

@greggh anyway u could share a session this happened?

opencode export > session.json

Are you using any plugins that could be interferring?

@rekram1-node commented on GitHub (Jan 2, 2026): @greggh anyway u could share a session this happened? `opencode export > session.json` Are you using any plugins that could be interferring?
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@FurryWolfX commented on GitHub (Jan 3, 2026):

I also encountered the same issue. It doesn't happen all the time, and I'm not sure what triggers it.

@FurryWolfX commented on GitHub (Jan 3, 2026): I also encountered the same issue. It doesn't happen all the time, and I'm not sure what triggers it.
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@heimoshuiyu commented on GitHub (Jan 3, 2026):

I have also encountered this situation, especially when the context is long (>128k). I guess this is because glm4.7 was further trained based on glm4.5, and glm4.5 only supports a 128k context. This also explains why glm4.7’s accuracy declines beyond 100k, starts speaking nonsense, and mixes Chinese and English.

This is purely speculation without any evidence. Basically, when the context reaches around 100k, I manually execute /compact to avoid this issue.

@heimoshuiyu commented on GitHub (Jan 3, 2026): I have also encountered this situation, especially when the context is long (>128k). I guess this is because glm4.7 was further trained based on glm4.5, and glm4.5 only supports a 128k context. This also explains why glm4.7’s accuracy declines beyond 100k, starts speaking nonsense, and mixes Chinese and English. This is purely speculation without any evidence. Basically, when the context reaches around 100k, I manually execute /compact to avoid this issue.
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@greggh commented on GitHub (Jan 3, 2026):

@greggh anyway u could share a session this happened?

opencode export > session.json

Are you using any plugins that could be interferring?

I can make up a fake session later, my real work that this is happening on I can't share (I don't own, contract, ...). I'll grab some other code and get it to the point it fails.

As for consistency, I get it more than 10 times a day.

@greggh commented on GitHub (Jan 3, 2026): > [@greggh](https://github.com/greggh) anyway u could share a session this happened? > > `opencode export > session.json` > > Are you using any plugins that could be interferring? I can make up a fake session later, my real work that this is happening on I can't share (I don't own, contract, ...). I'll grab some other code and get it to the point it fails. As for consistency, I get it more than 10 times a day.
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@ahmedrowaihi commented on GitHub (Jan 3, 2026):

Ahhh GLM-4.7 on Zai cofing plan | +2

Image
@ahmedrowaihi commented on GitHub (Jan 3, 2026): Ahhh GLM-4.7 on Zai cofing plan | +2 <img width="780" height="84" alt="Image" src="https://github.com/user-attachments/assets/27f678d4-7cad-4e76-a089-e45e969d66d5" />
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@gsxdsm commented on GitHub (Jan 3, 2026):

Happening on my end also

@gsxdsm commented on GitHub (Jan 3, 2026): Happening on my end also
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 3, 2026):

anyway u could share a session this happened?

opencode export > session.json

@rekram1-node commented on GitHub (Jan 3, 2026): anyway u could share a session this happened? opencode export > session.json
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@ramarivera commented on GitHub (Jan 4, 2026):

@rekram1-node I was having this issue and I created a draft PR that right now fixes it like 60% of the time https://github.com/anomalyco/opencode/pull/6883 (not 100% cuz I stopped when I saw a similar issue was closed). happy to move it forward if there is interest and alignment in the fix this way :)

@ramarivera commented on GitHub (Jan 4, 2026): @rekram1-node I was having this issue and I created a draft PR that right now fixes it like 60% of the time https://github.com/anomalyco/opencode/pull/6883 (not 100% cuz I stopped when I saw a similar issue was closed). happy to move it forward if there is interest and alignment in the fix this way :)
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@ramarivera commented on GitHub (Jan 4, 2026):

So as per @rekram1-node , the fix is not correct

@ramarivera commented on GitHub (Jan 4, 2026): So as per @rekram1-node , the fix is not correct
yindo commented 2026-02-16 17:42:40 -05:00
Author
Owner
Copy Link
Copy Source

@greggh commented on GitHub (Jan 7, 2026):

anyway u could share a session this happened?

opencode export > session.json

Sorry for the delay, got busy. Here is a log of a session I did yesterday just to attempt to get it to break the same way it is for some of us. I exported the session right after it had the error, so its in the last message. I had it just playing around with my GitHub skill.

ses_46b95350fffeq8T95l1hKVHwsM.md

@greggh commented on GitHub (Jan 7, 2026): > anyway u could share a session this happened? > > opencode export > session.json Sorry for the delay, got busy. Here is a log of a session I did yesterday just to attempt to get it to break the same way it is for some of us. I exported the session right after it had the error, so its in the last message. I had it just playing around with my GitHub skill. [ses_46b95350fffeq8T95l1hKVHwsM.md](https://github.com/user-attachments/files/24482737/ses_46b95350fffeq8T95l1hKVHwsM.md)
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@greggh commented on GitHub (Jan 10, 2026):

How is this going for others? I am still having the issue, but not as often. Maybe a 20% decrease in the amount of these errors since I reported it.

@greggh commented on GitHub (Jan 10, 2026): How is this going for others? I am still having the issue, but not as often. Maybe a 20% decrease in the amount of these errors since I reported it.
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@rickross commented on GitHub (Jan 10, 2026):

anyway u could share a session this happened?

opencode export > session.json

Do you need more session examples of this bug occurring, @rekram1-node ?

It has been happening to me, and I haven't yet figured out how to get out of it.

GLM-thinking-tools-errors.md

@rickross commented on GitHub (Jan 10, 2026): > anyway u could share a session this happened? > > opencode export > session.json Do you need more session examples of this bug occurring, @rekram1-node ? It has been happening to me, and I haven't yet figured out how to get out of it. [GLM-thinking-tools-errors.md](https://github.com/user-attachments/files/24545633/GLM-thinking-tools-errors.md)
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@autistarum commented on GitHub (Jan 10, 2026):

I think the issue in general with GLM 4.7 is that around 55-60%, e.g. >100K it degenerates, becomes confused and renders useless. It does not limit to tool use, it forgets the whole project context at the times, instructions, etc. and so far this behavior has been consistent for all my sessions. Granted, I only have had a few session with this model so far but this certainly does not look good.

@autistarum commented on GitHub (Jan 10, 2026): I think the issue in general with GLM 4.7 is that around 55-60%, e.g. >100K it degenerates, becomes confused and renders useless. It does not limit to tool use, it forgets the whole project context at the times, instructions, etc. and so far this behavior has been consistent for all my sessions. Granted, I only have had a few session with this model so far but this certainly does not look good.
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 10, 2026):

@rickross can u send the actual export using the command I sent? You just sent a markdown transcript, I need json exports using the command I attached

@rekram1-node commented on GitHub (Jan 10, 2026): @rickross can u send the actual export using the command I sent? You just sent a markdown transcript, I need json exports using the command I attached
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@rickross commented on GitHub (Jan 10, 2026):

@rickross can u send the actual export using the command I sent? You just sent a markdown transcript, I need json exports using the command I attached

I'm sorry @rekram1-node but that session is no longer available. If I see it again I will capture that way forr you. Thanks for looking into this.

@rickross commented on GitHub (Jan 10, 2026): > [@rickross](https://github.com/rickross) can u send the actual export using the command I sent? You just sent a markdown transcript, I need json exports using the command I attached I'm sorry @rekram1-node but that session is no longer available. If I see it again I will capture that way forr you. Thanks for looking into this.
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@LegendEvent commented on GitHub (Jan 27, 2026):

how consistent is this?

this is about 120-130k context. Only then this appears

@LegendEvent commented on GitHub (Jan 27, 2026): > how consistent is this? this is about 120-130k context. Only then this appears
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@greggh commented on GitHub (Jan 27, 2026):

how consistent is this?

this is about 120-130k context. Only then this appears

This is the same for me.

@greggh commented on GitHub (Jan 27, 2026): > > how consistent is this? > > this is about 120-130k context. Only then this appears This is the same for me.
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@LegendEvent commented on GitHub (Jan 28, 2026):

Did anyone checked if this also happens in any other agentic coding Environment besides opencode? I guess this is not a opencode only problem. I think this is an problem within the model itself. Fastes workaround is to set the Context lenght to 128000 instead of 200000

@LegendEvent commented on GitHub (Jan 28, 2026): Did anyone checked if this also happens in any other agentic coding Environment besides opencode? I guess this is not a opencode only problem. I think this is an problem within the model itself. Fastes workaround is to set the Context lenght to 128000 instead of 200000
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@greggh commented on GitHub (Jan 28, 2026):

Did anyone checked if this also happens in any other agentic coding Environment besides opencode? I guess this is not a opencode only problem. I think this is an problem within the model itself. Fastes workaround is to set the Context lenght to 128000 instead of 200000

This is also happening on other models in OpenCode, like Kimi K2.

@greggh commented on GitHub (Jan 28, 2026): > Did anyone checked if this also happens in any other agentic coding Environment besides opencode? I guess this is not a opencode only problem. I think this is an problem within the model itself. Fastes workaround is to set the Context lenght to 128000 instead of 200000 This is also happening on other models in OpenCode, like Kimi K2.
yindo commented 2026-02-16 17:42:41 -05:00
Author
Owner
Copy Link
Copy Source

@bdwelle commented on GitHub (Feb 5, 2026):

I'm getting the same thing, e.g.

Thinking: bash<arg_key>command</arg_key><arg_value>./split-mbox-emails.py 1-to-split/*.mbox 2>&1 | head -10</arg_value><arg_key>description</arg_key><arg_value>Test split script on glob pattern</arg_value></tool_call>

@bdwelle commented on GitHub (Feb 5, 2026): I'm getting the same thing, e.g. `Thinking: bash<arg_key>command</arg_key><arg_value>./split-mbox-emails.py 1-to-split/*.mbox 2>&1 | head -10</arg_value><arg_key>description</arg_key><arg_value>Test split script on glob pattern</arg_value></tool_call>`
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#4114
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?